© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12679
    Prev
    Next
    INDEX
    Explanations

    expressions indicating actions or events, particularly in a sports or competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.06
    2:0.05
    3:0.13
    4:0.05
    5:0.03
    6:0.20
    7:0.08
    8:0.03
    9:0.06
    10:0.09
    11:0.10
    Negative Logits
     CFR
    -3.16
     Canadian
    -2.99
     Rule
    -2.91
     Urug
    -2.91
     MLS
    -2.87
     rule
    -2.84
     CFL
    -2.79
     Canada
    -2.76
     Uruguay
    -2.73
     Bild
    -2.71
    POSITIVE LOGITS
    ォ
    2.77
    oice
    2.65
    onew
    2.65
    VOL
    2.59
    vol
    2.58
     Lump
    2.54
    milo
    2.46
    な
    2.45
     Shelter
    2.43
     サーティワン
    2.42
    Activations Density 0.001%

    No Known Activations